© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99595
    Prev
    Next
    INDEX
    Explanations

    relates to / active / после

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -2.36
    有些不
    -1.33
    なども
    -1.33
     by
    -1.30
    少々
    -1.25
     in
    -1.25
     when
    -1.24
    が少ない
    -1.23
     ”
    -1.23
     schrijven
    -1.23
    POSITIVE LOGITS
    從
    1.48
     със
    1.36
    从
    1.34
    بیشتر
    1.25
    laient
    1.24
     antworte
    1.23
    我們
    1.20
    nande
    1.20
     recurrir
    1.19
    词汇
    1.18
    Activations Density 0.325%

    No Known Activations